fix: don't fall back when a model is explicitly configured in registry

Previously any backend error would silently fall back to Claude.
Now if the user has a model configured via the model registry, errors
propagate to the UI so the actual problem is visible rather than hidden
behind a transparent backend switch.

Fallback still applies when using the default/auto backend with no
registry config.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

cortex/llm_client.py

@@ -87,9 +87,15 @@ async def complete(
         return response, primary
     except Exception as e:
         err_str = str(e)
-        logger.warning("%s failed (%s) — falling back to %s", primary, e, fallback)
         if primary == "claude" and any(k in err_str for k in ("401", "authenticate", "expired", "OAuth")):
             await event_bus.publish({"type": "claude_auth_expired"})
+        # Only fall back when using a default/auto backend.
+        # If the user has explicitly configured a model via the registry,
+        # surface the error so they know something is wrong.
+        if resolved_cfg is not None:
+            logger.error("%s failed (no fallback — model explicitly configured): %s", primary, e)
+            raise
+        logger.warning("%s failed (%s) — falling back to %s", primary, e, fallback)
         response = await _dispatch(fallback, system_prompt, messages, None)
         return response, fallback